1f3a923f57a112439828d59acb94ba48dc2d9556b5fad2fb6005322681ef255e

README.md

@@ -0,0 +1,28 @@
+---
+base_model: Qwen/Qwen2.5-1.5B
+language:
+- en
+library_name: transformers
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-Math-1.5B/blob/main/LICENSE
+pipeline_tag: text-generation
+tags:
+- mlx
+---
+
+# mlx-community/Qwen2.5-Math-1.5B-bf16
+
+The Model [mlx-community/Qwen2.5-Math-1.5B-bf16](https://huggingface.co/mlx-community/Qwen2.5-Math-1.5B-bf16) was converted to MLX format from [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) using mlx-lm version **0.18.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Qwen2.5-Math-1.5B-bf16")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,28 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 4096,
+    "max_window_layers": 21,
+    "model_type": "qwen2",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000,
+    "sliding_window": 4096,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.0",
+    "use_cache": true,
+    "use_mrope": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

model.safetensors.index.json

@@ -0,0 +1,345 @@
+{
+    "metadata": {
+        "total_size": 3087428608
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.24.input_layernorm.weight": "model.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.25.input_layernorm.weight": "model.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.26.input_layernorm.weight": "model.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.27.input_layernorm.weight": "model.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}